How to connect Eden AI to Claude Cowork

Cowork is Anthropic's AI agent for knowledge work. Think of it as Claude Code for everything else. It works autonomously with your computer, local files, and applications to accomplish complex tasks.

This guide walks you through the easiest and most secure way to connect your Eden AI account to Cowork via Composio Connect, enabling it to classify support tickets using Eden AI, generate product images with Eden AI, transcribe meeting audio through Eden AI, and more such actions on your behalf without compromising your account security.

Connecting Eden AI to Claude Cowork

1. Open Customize

In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.

2. Add the Composio MCP server

Click Add custom connector and paste in the Composio MCP server URL:

Claude Cowork is Anthropic's agent for general knowledge work. It can use your computer, files, and connected applications to complete longer-running tasks across your work tools.

With Composio Connect, Cowork can securely access apps like Eden AI through MCP without you sharing account credentials directly with the agent.

The Eden AI MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Eden AI account. It provides structured and secure access to your AI models, generated responses, safety checks, model catalog, and usage data, so your agent can generate text, create embeddings, moderate content, discover model capabilities, and track costs on your behalf.

• Text generation and response retrieval: Have your agent generate text with supported models, continue saved responses, and retrieve earlier results for follow-up work.
• Embeddings for search and analysis: Direct your agent to turn individual texts or batches into embeddings for semantic search, clustering, and similarity tasks.
• Content safety checks: Let the agent moderate one or more texts, identify flagged safety categories, and review confidence scores before using the content.
• Model and capability discovery: Instruct your agent to find available models and compare supported features, providers, pricing, and regions before choosing one.
• Usage planning and cost tracking: Have your agent count tokens before generating content, check account credits, and review consumption by provider or feature over a selected period.